ABSTRACT
Automatically extracting the headline of online web articles has many applications in web mining and information retrieval. In this paper, we developed a content-based and domain-and language-independent approach, TitleFinder, for unsupervised extraction of the headline of web articles. TitleFinder starts by using a heuristic to select a candidate headline. In a second step the contents of each text fragment in the HTML file are compared to the candidate headline. We implemented four types of similarity for this comparison: two variations of the cosine similarity based on tf and tf-idf weighting schemata, an overlap scoring similarity and an aggregated metric combining the scores of the previous three similarities. Our method achieves high performance in terms of effectiveness and efficiency and outperforms approaches operating on structural and visual features on a test set consisting of 11,218 news web pages from 15 different domains.
- S. Changuel, N. Labroche, and B. Bouchon-Meunier. A general learning method for automatic title extraction from html pages. In 6th International Conference of Machine Learning and Data Mining in Pattern Recognition, pages 704--718. Springer, 2009. Google ScholarDigital Library
- C. Fairon, H. Naets, A. Kilgarriff, and G.-M. de Schryver, editors. WAC3: Proceedings of the 3rd web as corpus workshop, incorporating cleaneval. Presses universitaires de Louvain, Sept. 2007.Google Scholar
- J. Fan, P. Luo, and P. Joshi. Title identification of web article pages using html and visual features. Proc. SPIE 7879, 78790K (2011).Google ScholarCross Ref
- J. Fan, P. Luo, S. H. Lim, S. Liu, J. Parag, and J. Liu. Article clipper: a system for web article extraction. In Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 743--746. ACM, 2011. Google ScholarDigital Library
- T. Gottron. Evaluating content extraction on HTML documents. In ITA '07: Proceedings of the 2nd International Conference on Internet Technologies and Applications, pages 123--132, Sept. 2007.Google Scholar
- T. Gottron. Bridging the gap: From multi document template detection to single document content extraction. In EuroIMSA '08: Proceedings of the IASTED Conference on Internet and Multimedia Systems and Applications 2008, pages 66--71. ACTA Press, Calgary, Mar. 2008. Google ScholarDigital Library
- T. Gottron. Content code blurring: A new approach to content extraction. In DEXA '08: 19th International Workshop on Database and Expert Systems Applications, IEEE Computer Society, pages 29--33. IEEE Computer Society, Sept. 2008. Google ScholarDigital Library
- Y. Hu, H. Li, Y. Cao, L. Teng, D. Meyerzon, and Q. Zheng. Automatic extraction of titles from general documents using machine learning. ACM/IEEE Joint Conference on Digital Libraries, JCDL 2005, pages 145--154, 2005. Google ScholarDigital Library
- Y. Hu, G. Xin, R. Song, G. Hu, S. Shi, Y. Cao, and H. Li. Title extraction from bodies of html documents and its application to web page retrieval. In SIGIR 2005: Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information, pages 250--257. ACM, August 2005. Google ScholarDigital Library
- H. Ibrahim, K. Darwish, and A.-R. Madany. Automatic extraction of textual elements from news web pages. In Proceedings of the International Conference on Language Resources and Evaluation, LREC 2008, 2008.Google Scholar
- C. Manning, P. Raghavan, and H. Schütze. An Introduction to Information Retrieval. 2009. Google ScholarDigital Library
- H. Mohammadzadeh, T. Gottron, F. Schweiggert, and G. Nakhaeizadeh. A fast and accurate approach for main content extraction based on character encoding. In TIR'11: Proccedings of the 8th International Workshop on Text-based Information Retrieval (DEXA'11). IEEE Computer Society, pages 167--171, 2011. Google ScholarDigital Library
- H. Mohammadzadeh, T. Gottron, F. Schweiggert, and G. Nakhaeizadeh. The impact of source code normalization on main content extraction. In WEBIST'12: 8th International Conference on Web Information Systems and Technologies, pages 677--682, 2012.Google Scholar
- J. Moreno, K. Deschacht, and M. Moens. Language independent content extraction from web pages. In Proceeding of the 9th Dutch-Belgian Information Retrieval Workshop, pages 50--55, 2009.Google Scholar
- G. Salton, A. Wong, and C. S. Yang. A vector space model for automatic indexing. Communications of the ACM, 18:613--620, 1975. Google ScholarDigital Library
- F. Sun, D. Song, and L. Liao. Dom based content extraction via text density. In Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval, SIGIR '11, pages 245--254, New York, NY, USA, 2011. ACM. Google ScholarDigital Library
- T. Weninger, W. H. Hsu, and J. Han. Cetr: content extraction via tag ratios. In Proceedings of the 19th International Conference on World Wide Web, pages 971--980. ACM, 2010. Google ScholarDigital Library
- Y. Xue, Y. Hu, G. Xin, R. Song, S. Shi, Y. Cao, C.-Y. Lin, and H. Li. Web page title extraction and its application. Inf. Process. Manage., 43(5):1332--1347, 2007. Google ScholarDigital Library
- Z. Zhang, M. Sun, and S. Liu. Automatic content based title extraction for chinese documents using support vector machine. In Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, pages 553--558. IEEE, 2005.Google ScholarCross Ref
Index Terms
- TitleFinder: extracting the headline of news web pages based on cosine similarity and overlap scoring similarity
Recommendations
Fuzzy logic-based approach to develop hybrid similarity measure for efficient information retrieval
A similarity measure is used in information retrieval systems to retrieve and rank the relevant documents. In this paper, a new fuzzy-based approach to develop hybrid similarity measure is proposed and implemented. The proposed approach overcomes the ...
Learning similarity with cosine similarity ensemble
This paper proposes a cosine similarity ensemble (CSE) method to learn similarity.CSE is a selective ensemble and combines multiple cosine similarity learners.A learner redefines the pattern vectors and determines its threshold adaptively.Experimental ...
Fuzzy logic based multi document summarization with improved sentence scoring and redundancy removal technique
Highlights- Statistical feature based extractive approach for multi-document summarization.
AbstractNowadays abundant amount of information is available on Internet which makes it difficult for the users to locate desired information. Automatic methods are needed to efficiently sieve and scavenge useful information from the Internet. ...
Comments